Frame the 3x3 plus-sign classifier experiment

Success is not “I followed the tutorial.” Success is producing evidence that: plus fixtures score positive; blank/noise fixtures do not. The accepted input is narrow on purpose: 3×3 binary grids and a hand-built feature or weight pattern. That narrowness is what lets you inspect every field and prevents a toy demo from being narrated as a production system.

Record the baseline you must beat: pixel-sum threshold accuracy on the same four images. If the finished artifact cannot beat that baseline on the fixture below, stop and revise the claim before writing more code.

plus=[[0,1,0],[1,1,1],[0,1,0]]
print('pixels',sum(map(sum,plus)),'shape',len(plus),len(plus[0]))

Expected evidence: fragile pixel classifier. Treat the printout as a claim about this fixture, not as proof that the toolchain merely started.

For the 3×3 plus-sign image classifier, a decorative win often looks like a clean run that never checks accuracy on a fixed four-image set; feature activations printed. Write the metric down now so later pages cannot redefine success after the fact. Also note the operational threat you will eventually gate on: claiming 'computer vision' production readiness from 3×3 toys.

For computer-sees, write the claim on a sticky note in this exact shape: “Given 3×3 binary grids and a hand-built feature or weight pattern, the 3x3 plus-sign classifier will …”. Fill the ellipsis with the observable part of: plus fixtures score positive; blank/noise fixtures do not. Tape the baseline beside it: pixel-sum threshold accuracy on the same four images. If someone later replaces your metric with a vibe check, the sticky note is how you push back.

Also sketch the one-sentence user story: a person uses this output to classify tiny binary images as plus vs not-plus with inspectable features. If that sentence needs a dashboard, a model zoo, or five services, the lab scope is too wide—shrink the fixture (plus, blank, and distractor 3×3 grids) until the story fits on one screen.

Decide now whether live network calls are allowed on page 1. For this lab they usually are not; inventory and contracts should run offline against plus, blank, and distractor 3×3 grids. Note the metric you will eventually require (accuracy on a fixed four-image set; feature activations printed) so page 4 cannot invent a softer target. The characteristic failure to keep in mind is overfitting to one plus orientation, or leaking test grids into template design.

At the experiment brief stage for computer-sees, the job is narrower than finishing a product demo. You are creating one progressive evidence piece about plus, blank, and distractor 3×3 grids that later pages inherit without redefining success. Keep that fixture small enough to inspect by hand, keep outputs copy-pasteable as text, and refuse to narrate this baseline as if it were a production SLA: pixel-sum threshold accuracy on the same four images.

For this page specifically, success looks like a falsifiable claim and baseline written before coding while still centering the user decision to classify tiny binary images as plus vs not-plus with inspectable features. If you cannot point to a file, command, or assertion that proves that for the 3x3 plus-sign classifier, stay on this page instead of advancing.

Glossary: computer vision · Glossary: convolutional neural network

Next